Propose a patch

Evidence

The sandbox observed nothing beyond the static findings; the proposal cites those.

diff --git a/package.json b/package.json
--- a/package.json
+++ b/package.json
@@ -1,1 +1,0 @@
-{"name":"@flyle/ai-cx-mcp","version":"0.1.0","description":"MCP server for the Flyle AI CX public API","keywords":["flyle","mcp","modelcontextprotocol"],"license":"SEE LICENSE IN LICENSE","author":"Fl
diff --git a/main.js b/main.js
--- a/main.js
+++ b/main.js
@@ -85,1 +85,0 @@
-`,e.NAME_START_CHAR=`:A-Z_a-zÀ-ÖØ-öø-˿Ͱ-ͽͿ-῿‌‍⁰-↏Ⰰ-⿯、-퟿豈-﷏ﷰ-�𐀀-󯿿`,e.NAME_CHAR=`-`+e.NAME_START_CHAR+`.0-9·̀-ͯ‿-⁀`,e.CHAR_RE=RegExp(`^[`+e.CHAR+`]$`,`u`),e.S_RE=RegExp(`^[`+e.S+`]+$`,`u`),e.NAME_STAR
@@ -94,1 +93,0 @@
-`,e.NAME_START_CHAR=`:A-Z_a-zÀ-ÖØ-öø-˿Ͱ-ͽͿ-῿‌‍⁰-↏Ⰰ-⿯、-퟿豈-﷏ﷰ-�𐀀-󯿿`,e.NAME_CHAR=`-`+e.NAME_START_CHAR+`.0-9·̀-ͯ‿-⁀`,e.CHAR_RE=RegExp(`^[`+e.CHAR+`]$`,`u`),e.RESTRICTED_CHAR_RE=RegExp(`^[`+e.RESTRICTED
@@ -102,1 +100,0 @@
-Object.defineProperty(e,"__esModule",{value:!0}),e.NC_NAME_START_CHAR=`A-Z_a-zÀ-ÖØ-öø-˿Ͱ-ͽͿ-῿‌-‍⁰-↏Ⰰ-⿯、-퟿豈-﷏ﷰ-�𐀀-󯿿`,e.NC_NAME_CHAR=`-`+e.NC_NAME_START_CHAR+`.0-9·̀-ͯ‿-⁀`,e.NC_NAME_START_CHAR_RE=RegE

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.0. If the behavior is intended, declare it (host under permissions.network, a line in the README) instead of removing it; the next crawl scores declarations.

Issue / PR body

Title: ai-cx-mcp: URL with embedded credentials (KillerSkills verdict caution 69)

## What the honeypot observed
KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.5) and scored it **CAUTION 69/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/npm/ai-cx-mcp/0.1.0

## Findings with a location
- `package.json:1` · URL with embedded credentials — package.json:1 · URL with embedded credentials — may be phishing or credential leaking
- `main.js:102` · Hidden zero-width characters detected — main.js:102 · Hidden zero-width characters detected — may conceal content
- `main.js:85` · Hidden zero-width characters detected — main.js:85 · Hidden zero-width characters detected — may conceal content
- `main.js:94` · Hidden zero-width characters detected — main.js:94 · Hidden zero-width characters detected — may conceal content

## Proposed change
The attached patch removes the 4 lines above. If the behavior is intended, the fix is to declare it instead: list the host under `permissions.network` (or the MCP manifest) and say in the README why the package needs it; the next crawl will re-score it with the declaration taken into account.

## How this will be verified
Nothing is "verified safe" by assertion. When a new version is published, KillerSkills re-runs it in the honeypot and the verdict page updates; you can trigger it early from the verdict page ("Re-scan after I publish a fix"). Reply here or at [email protected] if you believe the verdict is wrong; disputes are reviewed by a person and the outcome is published on the verdict page.

_Proposed through killerskills.ai/threats by a user of the package, under their own GitHub account. The evidence is public; the package was never modified by KillerSkills._